Automatic Datapath Optimization using E-Graphs

TL;DR

This paper introduces an automated RTL datapath optimization method using E-Graphs and graph rewriting, achieving significant area reductions and generating multiple optimized architectures, streamlining the design process.

Contribution

It presents a novel automated approach leveraging E-Graphs for RTL optimization, capturing complex transformations and extending prior optimization techniques.

Findings

Achieves up to 71% reduction in circuit area.

Automatically reproduces typical manual optimizations.

Generates a library of optimized designs based on operand width.

Abstract

Manual optimization of Register Transfer Level (RTL) datapath is commonplace in industry but holds back development as it can be very time consuming. We utilize the fact that a complex transformation of one RTL into another equivalent RTL can be broken down into a sequence of smaller, localized transformations. By representing RTL as a graph and deploying modern graph rewriting techniques we can automate the circuit design space exploration, allowing us to discover functionally equivalent but optimized architectures. We demonstrate that modern rewriting frameworks can adequately capture a wide variety of complex optimizations performed by human designers on bit-vector manipulating code, including significant error-prone subtleties regarding the validity of transformations under complex interactions of bitwidths. The proposed automated optimization approach is able to reproduce the results of typical industrial manual optimization, resulting in a reduction in circuit area by up to 71%. Not only does our tool discover optimized RTL, but also correctly identifies that the optimal architecture to implement a given arithmetic expression can depend on the width of the operands, thus producing a library of optimized designs rather than the single design point typically generated by manual optimization. In addition, we demonstrate that prior academic work on maximally exploiting carry-save representation and on multiple constant multiplication are both generalized and extended, falling out as special cases of this paper.